@ -1,6 +1,8 @@
#include "common.h"
#include "llama.h"
#include <ctime>
int main(int argc, char ** argv) {
gpt_params params;
params.model = "models/llama-7B/ggml-model.bin";
@ -11,6 +11,7 @@
#include <cmath>
#include <cstdio>
#include <cstring>
#include <fstream>
#include <iostream>
#include <string>
@ -2,6 +2,7 @@
std::vector<float> softmax(const std::vector<float>& logits) {
std::vector<float> probs(logits.size());